End of training

README.md

@@ -3,9 +3,15 @@ library_name: transformers
 license: apache-2.0
 base_model: alignment-handbook/zephyr-7b-sft-full
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: zephyr-7b-align-scan-0.0-0.3-linear-3
   results: []
@@ -16,17 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-align-scan-0.0-0.3-linear-3
 
-This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8316
-- Rewards/chosen: -3.2765
-- Rewards/rejected: -4.2890
+- Loss: 0.8855
+- Rewards/chosen: -3.8900
+- Rewards/rejected: -5.1926
 - Rewards/accuracies: 0.3413
-- Rewards/margins: 1.0125
-- Logps/rejected: -94.3157
-- Logps/chosen: -84.5654
-- Logits/rejected: -2.4456
-- Logits/chosen: -2.4656
+- Rewards/margins: 1.3027
+- Logps/rejected: -97.0942
+- Logps/chosen: -86.4517
+- Logits/rejected: -2.4499
+- Logits/chosen: -2.4705
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 3.0,
+    "eval_logits/chosen": -2.470487117767334,
+    "eval_logits/rejected": -2.4498531818389893,
+    "eval_logps/chosen": -86.45170593261719,
+    "eval_logps/rejected": -97.09423065185547,
+    "eval_loss": 0.8855458498001099,
+    "eval_rewards/accuracies": 0.341269850730896,
+    "eval_rewards/chosen": -3.889953851699829,
+    "eval_rewards/margins": 1.3026951551437378,
+    "eval_rewards/rejected": -5.1926493644714355,
+    "eval_runtime": 137.5858,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 14.536,
+    "eval_steps_per_second": 0.458,
     "total_flos": 0.0,
     "train_loss": 0.4743386713994874,
     "train_runtime": 3246.9146,

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_logits/chosen": -2.470487117767334,
+    "eval_logits/rejected": -2.4498531818389893,
+    "eval_logps/chosen": -86.45170593261719,
+    "eval_logps/rejected": -97.09423065185547,
+    "eval_loss": 0.8855458498001099,
+    "eval_rewards/accuracies": 0.341269850730896,
+    "eval_rewards/chosen": -3.889953851699829,
+    "eval_rewards/margins": 1.3026951551437378,
+    "eval_rewards/rejected": -5.1926493644714355,
+    "eval_runtime": 137.5858,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 14.536,
+    "eval_steps_per_second": 0.458
+}

runs/Sep24_11-44-10_qa-a100-004.crc.nd.edu/events.out.tfevents.1727196315.qa-a100-004.crc.nd.edu.1827364.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb77121778605f7f36ecd67a343717f32f11c513e49ee245c130c9f742808c7a
+size 828